A multi-species benchmark for training and validating mass spectrometry proteomics machine learning models

preprint · ChemRxiv · 2024

preprint · ChemRxiv · 2024. Bo Wen et al. Training machine learning models for tasks such as de novo sequencing or spectral clustering requires large…
Date 2024-08-30
Type preprint
Venue ChemRxiv
Publisher ChemRxiv
Contribution benchmark
DOI 10.26434/chemrxiv-2024-z5b8m
Citations (OpenAlex) 1

Abstract

Training machine learning models for tasks such as de novo sequencing or spectral clustering requires large collections of confidently identified spectra. Here we describe a dataset of 2.8 million high-confidence peptide-spectrum matches derived from nine different species. The dataset is based on a previously described benchmark but has been re-processed to ensure consistent data quality and enforce separation of training and test peptides.

Authors

  1. Bo Wen · Baylor College of Medicine, University of Washington
  2. William Stafford Noble · University of Washington

Methods and tools

Cited by (1)

Seen in the charts

Back to the full map

Back to top